
#importing tensorflow
import tensorflow as tf
print(tf.__version__)

2.5.0


import warnings

warnings.filterwarnings("ignore")


import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
import tensorflow as tf
from sklearn import preprocessing
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from sklearn.metrics import accuracy_score, confusion_matrix, precision_score, recall_score, f1_score, precision_recall_curve, auc
import matplotlib.pyplot as plt
from tensorflow.keras import optimizers
from sklearn.decomposition import PCA
import seaborn as sns
import keras
import tensorflow as tf
from keras import backend as K
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import Adam

from sklearn.preprocessing import StandardScaler


from google.colab import drive
drive.mount('/content/drive')

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).


#Defining the path of the dataset
project_path = '/content/drive/My Drive/AIML/Project6/'
dataset_file = project_path + 'bank.csv'


churn_df=pd.read_csv (dataset_file) #read in data


churn_df.sample(5)


churn_df.shape

(10000, 14)


churn_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 14 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   RowNumber        10000 non-null  int64  
 1   CustomerId       10000 non-null  int64  
 2   Surname          10000 non-null  object 
 3   CreditScore      10000 non-null  int64  
 4   Geography        10000 non-null  object 
 5   Gender           10000 non-null  object 
 6   Age              10000 non-null  int64  
 7   Tenure           10000 non-null  int64  
 8   Balance          10000 non-null  float64
 9   NumOfProducts    10000 non-null  int64  
 10  HasCrCard        10000 non-null  int64  
 11  IsActiveMember   10000 non-null  int64  
 12  EstimatedSalary  10000 non-null  float64
 13  Exited           10000 non-null  int64  
dtypes: float64(2), int64(9), object(3)
memory usage: 1.1+ MB


for feature in churn_df.columns: # Loop through all columns in the dataframe
    if churn_df[feature].dtype == 'object': # Only apply for columns with categorical strings
        churn_df[feature] = pd.Categorical(churn_df[feature])# Change to categorical varible
churn_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 14 columns):
 #   Column           Non-Null Count  Dtype   
---  ------           --------------  -----   
 0   RowNumber        10000 non-null  int64   
 1   CustomerId       10000 non-null  int64   
 2   Surname          10000 non-null  category
 3   CreditScore      10000 non-null  int64   
 4   Geography        10000 non-null  category
 5   Gender           10000 non-null  category
 6   Age              10000 non-null  int64   
 7   Tenure           10000 non-null  int64   
 8   Balance          10000 non-null  float64 
 9   NumOfProducts    10000 non-null  int64   
 10  HasCrCard        10000 non-null  int64   
 11  IsActiveMember   10000 non-null  int64   
 12  EstimatedSalary  10000 non-null  float64 
 13  Exited           10000 non-null  int64   
dtypes: category(3), float64(2), int64(9)
memory usage: 1001.7 KB


for feature in churn_df.columns:
    if churn_df[feature].name in churn_df.select_dtypes(include='category').columns:
        print(churn_df[feature].value_counts())
        print('-'*30)

Smith        32
Martin       29
Scott        29
Walker       28
Brown        26
             ..
Perreault     1
Perkin        1
Percy         1
Hardacre      1
Fancher       1
Name: Surname, Length: 2932, dtype: int64
------------------------------
France     5014
Germany    2509
Spain      2477
Name: Geography, dtype: int64
------------------------------
Male      5457
Female    4543
Name: Gender, dtype: int64
------------------------------


churn_df.isna().sum()

RowNumber          0
CustomerId         0
Surname            0
CreditScore        0
Geography          0
Gender             0
Age                0
Tenure             0
Balance            0
NumOfProducts      0
HasCrCard          0
IsActiveMember     0
EstimatedSalary    0
Exited             0
dtype: int64


churn_df.nunique()

RowNumber          10000
CustomerId         10000
Surname             2932
CreditScore          460
Geography              3
Gender                 2
Age                   70
Tenure                11
Balance             6382
NumOfProducts          4
HasCrCard              2
IsActiveMember         2
EstimatedSalary     9999
Exited                 2
dtype: int64


churn_df.describe()


churn_df.describe(include=['category']).T


#Function to create Histogram and Boxplot
def histogram_boxplot(feature, figsize=(10,5), bins = None):
    """ Boxplot and histogram combined
    feature: 1-d feature array
    figsize: size of fig (default (9,8))
    bins: number of bins (default None / auto)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(nrows = 2, 
                                           sharex = True, 
                                           gridspec_kw = {"height_ratios": (.25, .75)}, 
                                           figsize = figsize 
                                           )
    sns.boxplot(feature, ax=ax_box2, showmeans=True, color='violet') 
    sns.distplot(feature, kde=F, ax=ax_hist2, bins=bins,palette="winter") if bins else sns.distplot(feature, kde=False, ax=ax_hist2)
    ax_hist2.axvline(np.mean(feature), color='green', linestyle='--') 
    ax_hist2.axvline(np.median(feature), color='black', linestyle='-')


histogram_boxplot(churn_df['CreditScore'])


histogram_boxplot(churn_df['Age'])


histogram_boxplot(churn_df['Tenure'])


histogram_boxplot(churn_df['Balance'])


histogram_boxplot(churn_df['NumOfProducts'])


histogram_boxplot(churn_df['EstimatedSalary'])


# select numerical columns
all_col = churn_df.select_dtypes(include=np.number).columns.tolist()

fig, axes = plt.subplots(6, 2,  figsize=(20, 15))
fig.suptitle('CDF plot of numerical variables', fontsize=20)
counter = 0
for ii in range(6):
    sns.ecdfplot(ax=axes[ii][0],x=churn_df[all_col[counter]])
    counter = counter+1
    if counter != 11:
        sns.ecdfplot(ax=axes[ii][1],x=churn_df[all_col[counter]])
        counter = counter+1
    else:
        pass


fig.tight_layout(pad=2.0)


def perc_on_bar(feature):
 
    sns.set(rc={'figure.figsize':(9,3)})
    ax=sns.countplot(x=feature, data=churn_df)
    
    total = len(feature) 
    for p in ax.patches:
        percentage = '{:.1f}%'.format(100 * p.get_height()/total) 
        x = p.get_x() + p.get_width() / 2 - 0.25 
        y = p.get_y() + p.get_height()           
        ax.annotate(percentage, (x, y), size = 10) 
        
    plt.show()


perc_on_bar(churn_df['Geography'])


perc_on_bar(churn_df['Gender'])


perc_on_bar(churn_df['NumOfProducts'])


perc_on_bar(churn_df['HasCrCard'])


perc_on_bar(churn_df['IsActiveMember'])


perc_on_bar(churn_df['Exited'])


sns.pairplot(churn_df, height=3, diag_kind='kde',hue='Exited');


plt.figure(figsize=(10,10))
sns.heatmap(churn_df.corr(), annot=True, fmt=".2")
plt.show()


pd.crosstab(churn_df['Geography'],churn_df['Exited'],normalize='index')


pd.crosstab(churn_df['Gender'],churn_df['Exited'],normalize='index')


pd.crosstab(churn_df['Tenure'],churn_df['Exited'],normalize='index')


pd.crosstab(churn_df['NumOfProducts'],churn_df['Exited'],normalize='index')


pd.crosstab(churn_df['HasCrCard'],churn_df['Exited'],normalize='index')


pd.crosstab(churn_df['IsActiveMember'],churn_df['Exited'],normalize='index')


#Creating Fuction to plot continous varible distributions 
def cont_plot(feature): 
    
    sns.distplot(churn_df[churn_df['Exited']==0][feature],color='g',label='Retained Customer', bins=31)
    sns.distplot(churn_df[churn_df['Exited']==1][feature],color='r',label='Exited Customer', bins=31)
    plt.legend()
    plt.show()


cont_plot('CreditScore')


cont_plot('Age')


cont_plot('Balance')


cont_plot('EstimatedSalary')


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="CreditScore", x="Exited", data=churn_df, orient="vertical");


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Age", x="Exited", data=churn_df, orient="vertical");


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Tenure", x="Exited", data=churn_df, orient="vertical");


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Balance", x="Exited", data=churn_df, orient="vertical");


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="EstimatedSalary", x="Exited", data=churn_df, orient="vertical");


churn_df.groupby(['Exited']).mean()


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Age", x="Geography", data=churn_df, orient="vertical",hue='Exited');


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Age", x="Gender", data=churn_df, orient="vertical",hue='Exited');


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Age", x="NumOfProducts", data=churn_df, orient="vertical",hue='Exited');


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Age", x="IsActiveMember", data=churn_df, orient="vertical",hue='Exited');


churn_df.pivot_table('Age',index=['Geography','Exited'],aggfunc=['mean','count'])


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Balance", x="Geography", data=churn_df, orient="vertical",hue='Exited');


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Balance", x="Gender", data=churn_df, orient="vertical",hue='Exited');


sns.set(rc={"figure.figsize": (10, 7)})
sns.boxplot(y="Balance", x="IsActiveMember", data=churn_df, orient="vertical",hue='Exited');


churn_df.groupby(['Geography']).mean()


churn_df.info() #check data again

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 14 columns):
 #   Column           Non-Null Count  Dtype   
---  ------           --------------  -----   
 0   RowNumber        10000 non-null  int64   
 1   CustomerId       10000 non-null  int64   
 2   Surname          10000 non-null  category
 3   CreditScore      10000 non-null  int64   
 4   Geography        10000 non-null  category
 5   Gender           10000 non-null  category
 6   Age              10000 non-null  int64   
 7   Tenure           10000 non-null  int64   
 8   Balance          10000 non-null  float64 
 9   NumOfProducts    10000 non-null  int64   
 10  HasCrCard        10000 non-null  int64   
 11  IsActiveMember   10000 non-null  int64   
 12  EstimatedSalary  10000 non-null  float64 
 13  Exited           10000 non-null  int64   
dtypes: category(3), float64(2), int64(9)
memory usage: 1001.7 KB


data=churn_df.copy() #make copy of data before manipulations


#Map for Gender to make it numeric
gender_map={'Male':1,
         'Female':0}


data['Gender'].replace(gender_map,inplace=True)


data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 14 columns):
 #   Column           Non-Null Count  Dtype   
---  ------           --------------  -----   
 0   RowNumber        10000 non-null  int64   
 1   CustomerId       10000 non-null  int64   
 2   Surname          10000 non-null  category
 3   CreditScore      10000 non-null  int64   
 4   Geography        10000 non-null  category
 5   Gender           10000 non-null  int64   
 6   Age              10000 non-null  int64   
 7   Tenure           10000 non-null  int64   
 8   Balance          10000 non-null  float64 
 9   NumOfProducts    10000 non-null  int64   
 10  HasCrCard        10000 non-null  int64   
 11  IsActiveMember   10000 non-null  int64   
 12  EstimatedSalary  10000 non-null  float64 
 13  Exited           10000 non-null  int64   
dtypes: category(2), float64(2), int64(10)
memory usage: 1.0 MB


# Create one hot encoding

oneHotCols=["Geography"]


data=pd.get_dummies(data, columns=oneHotCols,drop_first=True)


data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 15 columns):
 #   Column             Non-Null Count  Dtype   
---  ------             --------------  -----   
 0   RowNumber          10000 non-null  int64   
 1   CustomerId         10000 non-null  int64   
 2   Surname            10000 non-null  category
 3   CreditScore        10000 non-null  int64   
 4   Gender             10000 non-null  int64   
 5   Age                10000 non-null  int64   
 6   Tenure             10000 non-null  int64   
 7   Balance            10000 non-null  float64 
 8   NumOfProducts      10000 non-null  int64   
 9   HasCrCard          10000 non-null  int64   
 10  IsActiveMember     10000 non-null  int64   
 11  EstimatedSalary    10000 non-null  float64 
 12  Exited             10000 non-null  int64   
 13  Geography_Germany  10000 non-null  uint8   
 14  Geography_Spain    10000 non-null  uint8   
dtypes: category(1), float64(2), int64(10), uint8(2)
memory usage: 1.1 MB


data.drop(["RowNumber",'CustomerId','Surname'] , axis=1,inplace=True)


# Spliting the target data
X_data = data.drop(columns=['Exited'])

y_data = data['Exited']


#printing the shape of the data 
print(y_data.shape)
print(X_data.shape)

(10000,)
(10000, 11)


X_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 11 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   CreditScore        10000 non-null  int64  
 1   Gender             10000 non-null  int64  
 2   Age                10000 non-null  int64  
 3   Tenure             10000 non-null  int64  
 4   Balance            10000 non-null  float64
 5   NumOfProducts      10000 non-null  int64  
 6   HasCrCard          10000 non-null  int64  
 7   IsActiveMember     10000 non-null  int64  
 8   EstimatedSalary    10000 non-null  float64
 9   Geography_Germany  10000 non-null  uint8  
 10  Geography_Spain    10000 non-null  uint8  
dtypes: float64(2), int64(7), uint8(2)
memory usage: 722.8 KB


# Scaling the data set before modeling
scaler=StandardScaler()
subset=X_data.copy()
subset_scaled=scaler.fit_transform(subset)


subset_scaled
subset_scaled_df=pd.DataFrame(subset_scaled,columns=subset.columns)


subset_scaled_df


subset_scaled_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 11 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   CreditScore        10000 non-null  float64
 1   Gender             10000 non-null  float64
 2   Age                10000 non-null  float64
 3   Tenure             10000 non-null  float64
 4   Balance            10000 non-null  float64
 5   NumOfProducts      10000 non-null  float64
 6   HasCrCard          10000 non-null  float64
 7   IsActiveMember     10000 non-null  float64
 8   EstimatedSalary    10000 non-null  float64
 9   Geography_Germany  10000 non-null  float64
 10  Geography_Spain    10000 non-null  float64
dtypes: float64(11)
memory usage: 859.5 KB


X_train, X_test, y_train, y_test = train_test_split(subset_scaled_df, y_data, test_size = 0.2, random_state = 8)


print(X_train.shape)
print(X_test.shape)
print(y_train.shape)
print(y_test.shape)

(8000, 11)
(2000, 11)
(8000,)
(2000,)


#initialize the model
model = Sequential()

# Creating input layer and first hiden layer
model.add(Dense(units=8, input_dim = 11,activation='relu'))   # input of 11 columns as shown above
# hidden layer
model.add(Dense(1,activation='sigmoid'))                        # binary classification for Churn or not

# Create optimizer with default learning rate
# Compile the model
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])

#create model summary 
model.summary()

Model: "sequential_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_5 (Dense)              (None, 8)                 96        
_________________________________________________________________
dense_6 (Dense)              (None, 1)                 9         
=================================================================
Total params: 105
Trainable params: 105
Non-trainable params: 0
_________________________________________________________________


#fitting the model
history=model.fit(X_train,y_train,batch_size=20,epochs=100,validation_split=0.2 )

Epoch 1/100
320/320 [==============================] - 2s 3ms/step - loss: 0.7461 - accuracy: 0.5341 - val_loss: 0.5356 - val_accuracy: 0.7688
Epoch 2/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4866 - accuracy: 0.8055 - val_loss: 0.4921 - val_accuracy: 0.7806
Epoch 3/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4386 - accuracy: 0.8171 - val_loss: 0.4779 - val_accuracy: 0.7856
Epoch 4/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4283 - accuracy: 0.8187 - val_loss: 0.4706 - val_accuracy: 0.7956
Epoch 5/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4440 - accuracy: 0.8025 - val_loss: 0.4636 - val_accuracy: 0.7931
Epoch 6/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4082 - accuracy: 0.8264 - val_loss: 0.4530 - val_accuracy: 0.8006
Epoch 7/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4168 - accuracy: 0.8256 - val_loss: 0.4413 - val_accuracy: 0.8044
Epoch 8/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3908 - accuracy: 0.8278 - val_loss: 0.4284 - val_accuracy: 0.8119
Epoch 9/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3757 - accuracy: 0.8406 - val_loss: 0.4149 - val_accuracy: 0.8225
Epoch 10/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3821 - accuracy: 0.8390 - val_loss: 0.4052 - val_accuracy: 0.8238
Epoch 11/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3604 - accuracy: 0.8467 - val_loss: 0.3964 - val_accuracy: 0.8363
Epoch 12/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3609 - accuracy: 0.8472 - val_loss: 0.3904 - val_accuracy: 0.8375
Epoch 13/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3476 - accuracy: 0.8569 - val_loss: 0.3846 - val_accuracy: 0.8381
Epoch 14/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3396 - accuracy: 0.8620 - val_loss: 0.3812 - val_accuracy: 0.8388
Epoch 15/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3516 - accuracy: 0.8556 - val_loss: 0.3811 - val_accuracy: 0.8419
Epoch 16/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3407 - accuracy: 0.8585 - val_loss: 0.3755 - val_accuracy: 0.8400
Epoch 17/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3528 - accuracy: 0.8535 - val_loss: 0.3759 - val_accuracy: 0.8425
Epoch 18/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3351 - accuracy: 0.8582 - val_loss: 0.3746 - val_accuracy: 0.8425
Epoch 19/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3440 - accuracy: 0.8618 - val_loss: 0.3741 - val_accuracy: 0.8431
Epoch 20/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3315 - accuracy: 0.8632 - val_loss: 0.3716 - val_accuracy: 0.8406
Epoch 21/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3279 - accuracy: 0.8627 - val_loss: 0.3711 - val_accuracy: 0.8431
Epoch 22/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3404 - accuracy: 0.8611 - val_loss: 0.3711 - val_accuracy: 0.8450
Epoch 23/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3416 - accuracy: 0.8593 - val_loss: 0.3709 - val_accuracy: 0.8438
Epoch 24/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3345 - accuracy: 0.8611 - val_loss: 0.3705 - val_accuracy: 0.8450
Epoch 25/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3198 - accuracy: 0.8678 - val_loss: 0.3691 - val_accuracy: 0.8462
Epoch 26/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3299 - accuracy: 0.8581 - val_loss: 0.3691 - val_accuracy: 0.8462
Epoch 27/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3299 - accuracy: 0.8654 - val_loss: 0.3695 - val_accuracy: 0.8475
Epoch 28/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3335 - accuracy: 0.8647 - val_loss: 0.3701 - val_accuracy: 0.8500
Epoch 29/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3317 - accuracy: 0.8627 - val_loss: 0.3690 - val_accuracy: 0.8481
Epoch 30/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3319 - accuracy: 0.8620 - val_loss: 0.3679 - val_accuracy: 0.8469
Epoch 31/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3320 - accuracy: 0.8626 - val_loss: 0.3684 - val_accuracy: 0.8487
Epoch 32/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3342 - accuracy: 0.8634 - val_loss: 0.3679 - val_accuracy: 0.8481
Epoch 33/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3289 - accuracy: 0.8653 - val_loss: 0.3698 - val_accuracy: 0.8494
Epoch 34/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3256 - accuracy: 0.8660 - val_loss: 0.3689 - val_accuracy: 0.8500
Epoch 35/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3257 - accuracy: 0.8649 - val_loss: 0.3670 - val_accuracy: 0.8481
Epoch 36/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3302 - accuracy: 0.8613 - val_loss: 0.3677 - val_accuracy: 0.8500
Epoch 37/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3230 - accuracy: 0.8708 - val_loss: 0.3686 - val_accuracy: 0.8506
Epoch 38/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3259 - accuracy: 0.8652 - val_loss: 0.3657 - val_accuracy: 0.8475
Epoch 39/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3368 - accuracy: 0.8570 - val_loss: 0.3687 - val_accuracy: 0.8469
Epoch 40/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3345 - accuracy: 0.8614 - val_loss: 0.3685 - val_accuracy: 0.8500
Epoch 41/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3366 - accuracy: 0.8658 - val_loss: 0.3677 - val_accuracy: 0.8494
Epoch 42/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3390 - accuracy: 0.8628 - val_loss: 0.3677 - val_accuracy: 0.8506
Epoch 43/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3280 - accuracy: 0.8610 - val_loss: 0.3683 - val_accuracy: 0.8494
Epoch 44/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3326 - accuracy: 0.8596 - val_loss: 0.3664 - val_accuracy: 0.8500
Epoch 45/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3215 - accuracy: 0.8670 - val_loss: 0.3673 - val_accuracy: 0.8481
Epoch 46/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3343 - accuracy: 0.8619 - val_loss: 0.3673 - val_accuracy: 0.8506
Epoch 47/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3325 - accuracy: 0.8586 - val_loss: 0.3663 - val_accuracy: 0.8500
Epoch 48/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3253 - accuracy: 0.8699 - val_loss: 0.3676 - val_accuracy: 0.8494
Epoch 49/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3277 - accuracy: 0.8619 - val_loss: 0.3650 - val_accuracy: 0.8487
Epoch 50/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3310 - accuracy: 0.8644 - val_loss: 0.3665 - val_accuracy: 0.8469
Epoch 51/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3350 - accuracy: 0.8577 - val_loss: 0.3649 - val_accuracy: 0.8481
Epoch 52/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3387 - accuracy: 0.8600 - val_loss: 0.3655 - val_accuracy: 0.8481
Epoch 53/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3292 - accuracy: 0.8604 - val_loss: 0.3667 - val_accuracy: 0.8481
Epoch 54/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3442 - accuracy: 0.8606 - val_loss: 0.3661 - val_accuracy: 0.8475
Epoch 55/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3284 - accuracy: 0.8623 - val_loss: 0.3650 - val_accuracy: 0.8500
Epoch 56/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3258 - accuracy: 0.8691 - val_loss: 0.3640 - val_accuracy: 0.8481
Epoch 57/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3281 - accuracy: 0.8636 - val_loss: 0.3643 - val_accuracy: 0.8450
Epoch 58/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3329 - accuracy: 0.8647 - val_loss: 0.3660 - val_accuracy: 0.8512
Epoch 59/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3265 - accuracy: 0.8655 - val_loss: 0.3649 - val_accuracy: 0.8506
Epoch 60/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3282 - accuracy: 0.8668 - val_loss: 0.3651 - val_accuracy: 0.8494
Epoch 61/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3283 - accuracy: 0.8680 - val_loss: 0.3652 - val_accuracy: 0.8475
Epoch 62/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3347 - accuracy: 0.8606 - val_loss: 0.3647 - val_accuracy: 0.8462
Epoch 63/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3463 - accuracy: 0.8518 - val_loss: 0.3659 - val_accuracy: 0.8494
Epoch 64/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3301 - accuracy: 0.8657 - val_loss: 0.3640 - val_accuracy: 0.8462
Epoch 65/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3236 - accuracy: 0.8665 - val_loss: 0.3652 - val_accuracy: 0.8469
Epoch 66/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3293 - accuracy: 0.8646 - val_loss: 0.3651 - val_accuracy: 0.8500
Epoch 67/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3236 - accuracy: 0.8653 - val_loss: 0.3640 - val_accuracy: 0.8494
Epoch 68/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3196 - accuracy: 0.8703 - val_loss: 0.3638 - val_accuracy: 0.8456
Epoch 69/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3243 - accuracy: 0.8679 - val_loss: 0.3647 - val_accuracy: 0.8519
Epoch 70/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3240 - accuracy: 0.8660 - val_loss: 0.3639 - val_accuracy: 0.8475
Epoch 71/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3322 - accuracy: 0.8613 - val_loss: 0.3632 - val_accuracy: 0.8425
Epoch 72/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3290 - accuracy: 0.8611 - val_loss: 0.3670 - val_accuracy: 0.8512
Epoch 73/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3319 - accuracy: 0.8589 - val_loss: 0.3660 - val_accuracy: 0.8506
Epoch 74/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3170 - accuracy: 0.8693 - val_loss: 0.3627 - val_accuracy: 0.8456
Epoch 75/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3261 - accuracy: 0.8645 - val_loss: 0.3629 - val_accuracy: 0.8475
Epoch 76/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3293 - accuracy: 0.8686 - val_loss: 0.3637 - val_accuracy: 0.8500
Epoch 77/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3309 - accuracy: 0.8612 - val_loss: 0.3648 - val_accuracy: 0.8481
Epoch 78/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3200 - accuracy: 0.8655 - val_loss: 0.3632 - val_accuracy: 0.8450
Epoch 79/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3252 - accuracy: 0.8609 - val_loss: 0.3647 - val_accuracy: 0.8481
Epoch 80/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3256 - accuracy: 0.8652 - val_loss: 0.3639 - val_accuracy: 0.8450
Epoch 81/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3236 - accuracy: 0.8651 - val_loss: 0.3647 - val_accuracy: 0.8487
Epoch 82/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3465 - accuracy: 0.8571 - val_loss: 0.3656 - val_accuracy: 0.8494
Epoch 83/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3199 - accuracy: 0.8708 - val_loss: 0.3646 - val_accuracy: 0.8481
Epoch 84/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3200 - accuracy: 0.8684 - val_loss: 0.3620 - val_accuracy: 0.8462
Epoch 85/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3166 - accuracy: 0.8702 - val_loss: 0.3638 - val_accuracy: 0.8475
Epoch 86/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3245 - accuracy: 0.8646 - val_loss: 0.3639 - val_accuracy: 0.8456
Epoch 87/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3270 - accuracy: 0.8625 - val_loss: 0.3619 - val_accuracy: 0.8438
Epoch 88/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3384 - accuracy: 0.8532 - val_loss: 0.3658 - val_accuracy: 0.8525
Epoch 89/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3141 - accuracy: 0.8692 - val_loss: 0.3636 - val_accuracy: 0.8469
Epoch 90/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3270 - accuracy: 0.8598 - val_loss: 0.3650 - val_accuracy: 0.8500
Epoch 91/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3298 - accuracy: 0.8645 - val_loss: 0.3636 - val_accuracy: 0.8475
Epoch 92/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3201 - accuracy: 0.8634 - val_loss: 0.3636 - val_accuracy: 0.8450
Epoch 93/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3426 - accuracy: 0.8542 - val_loss: 0.3647 - val_accuracy: 0.8487
Epoch 94/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3219 - accuracy: 0.8668 - val_loss: 0.3632 - val_accuracy: 0.8462
Epoch 95/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3277 - accuracy: 0.8655 - val_loss: 0.3638 - val_accuracy: 0.8475
Epoch 96/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3199 - accuracy: 0.8708 - val_loss: 0.3655 - val_accuracy: 0.8500
Epoch 97/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3291 - accuracy: 0.8647 - val_loss: 0.3635 - val_accuracy: 0.8469
Epoch 98/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3259 - accuracy: 0.8625 - val_loss: 0.3658 - val_accuracy: 0.8512
Epoch 99/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3267 - accuracy: 0.8594 - val_loss: 0.3637 - val_accuracy: 0.8481
Epoch 100/100
320/320 [==============================] - 1s 2ms/step - loss: 0.3138 - accuracy: 0.8695 - val_loss: 0.3629 - val_accuracy: 0.8475


# Capturing learning history per epoch
hist  = pd.DataFrame(history.history)
hist['epoch'] = history.epoch

# Plotting accuracy at different epochs
plt.plot(hist['loss'])
plt.plot(hist['val_loss'])
plt.legend(("train" , "valid") , loc =0)

<matplotlib.legend.Legend at 0x7fe3cf0e1c50>


score = model.evaluate(X_test, y_test)

63/63 [==============================] - 0s 2ms/step - loss: 0.3394 - accuracy: 0.8630


print(1-sum(y_test)/len(y_test),"would have been accuracy if we guessed all 0s")

0.7935 would have been accuracy if we guessed all 0s


def make_confusion_matrix(cf,
                          group_names=None,
                          categories='auto',
                          count=True,
                          percent=True,
                          cbar=True,
                          xyticks=True,
                          xyplotlabels=True,
                          sum_stats=True,
                          figsize=None,
                          cmap='Blues',
                          title=None):
    '''
    This function will make a pretty plot of an sklearn Confusion Matrix cm using a Seaborn heatmap visualization.
    Arguments
    '''


    # CODE TO GENERATE TEXT INSIDE EACH SQUARE
    blanks = ['' for i in range(cf.size)]

    if group_names and len(group_names)==cf.size:
        group_labels = ["{}\n".format(value) for value in group_names]
    else:
        group_labels = blanks

    if count:
        group_counts = ["{0:0.0f}\n".format(value) for value in cf.flatten()]
    else:
        group_counts = blanks

    if percent:
        group_percentages = ["{0:.2%}".format(value) for value in cf.flatten()/np.sum(cf)]
    else:
        group_percentages = blanks

    box_labels = [f"{v1}{v2}{v3}".strip() for v1, v2, v3 in zip(group_labels,group_counts,group_percentages)]
    box_labels = np.asarray(box_labels).reshape(cf.shape[0],cf.shape[1])


    # CODE TO GENERATE SUMMARY STATISTICS & TEXT FOR SUMMARY STATS
    if sum_stats:
        #Accuracy is sum of diagonal divided by total observations
        accuracy  = np.trace(cf) / float(np.sum(cf))

        #if it is a binary confusion matrix, show some more stats
        if len(cf)==2:
            #Metrics for Binary Confusion Matrices
            precision = cf[1,1] / sum(cf[:,1])
            recall    = cf[1,1] / sum(cf[1,:])
            f1_score  = 2*precision*recall / (precision + recall)
            stats_text = "\n\nAccuracy={:0.3f}\nPrecision={:0.3f}\nRecall={:0.3f}\nF1 Score={:0.3f}".format(
                accuracy,precision,recall,f1_score)
        else:
            stats_text = "\n\nAccuracy={:0.3f}".format(accuracy)
    else:
        stats_text = ""


    # SET FIGURE PARAMETERS ACCORDING TO OTHER ARGUMENTS
    if figsize==None:
        #Get default figure size if not set
        figsize = plt.rcParams.get('figure.figsize')

    if xyticks==False:
        #Do not show categories if xyticks is False
        categories=False


    # MAKE THE HEATMAP VISUALIZATION
    plt.figure(figsize=figsize)
    sns.heatmap(cf,annot=box_labels,fmt="",cmap=cmap,cbar=cbar,xticklabels=categories,yticklabels=categories)

    if xyplotlabels:
        plt.ylabel('True label')
        plt.xlabel('Predicted label' + stats_text)
    else:
        plt.xlabel(stats_text)
    
    if title:
        plt.title(title)


## Confusion Matrix 
import seaborn as sn
y_pred1 = model.predict(X_test)
for i in range(len(y_test)):
    if y_pred1[i]>0.5:
        y_pred1[i]=1 
    else:
        y_pred1[i]=0



cm2=confusion_matrix(y_test, y_pred1)
labels = ['True Negative','False Positive','False Negative','True Positive']
categories = [ 'Retained','Exited']
make_confusion_matrix(cm2, 
                      group_names=labels,
                      categories=categories, 
                      cmap='Blues')


#AUC ROC curve
from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve

DNN_roc_auc = roc_auc_score(y_test, model.predict(X_test))
fpr, tpr, thresholds = roc_curve(y_test, model.predict(X_test))

# calculate the g-mean for each threshold
gmeans = np.sqrt(tpr * (1-fpr))


# locate the index of the largest g-mean
ix = np.argmax(gmeans)
print('Best Threshold=%f, G-Mean=%.3f' % (thresholds[ix], gmeans[ix]))


plt.figure()

plt.scatter(fpr[ix], tpr[ix], marker='o', color='black', label='Best')
plt.plot(fpr, tpr, label='Model 1 (area = %0.2f)' % DNN_roc_auc)
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
plt.savefig('ROC')
plt.show()

Best Threshold=0.231908, G-Mean=0.797


y_pred1 = model.predict(X_test)
for i in range(len(y_test)):
    if y_pred1[i]>0.231908:
        y_pred1[i]=1 
    else:
        y_pred1[i]=0



cm2=confusion_matrix(y_test, y_pred1)
labels = ['True Negative','False Positive','False Negative','True Positive']
categories = [ 'Retained','Exited']
make_confusion_matrix(cm2, 
                      group_names=labels,
                      categories=categories, 
                      cmap='Blues')


from sklearn.utils import class_weight
class_weights = class_weight.compute_class_weight('balanced', np.unique(y_train), np.array([y_train.iloc[i] for i in range(len(y_train))]))
class_weights = dict(enumerate(class_weights))
class_weights

{0: 0.6273525721455459, 1: 2.4630541871921183}


#initialize the model
model2 = Sequential()

# Creating input layer and first hiden layer
model2.add(Dense(units=8, input_dim = 11,activation='relu',kernel_initializer='he_normal'))   # input of 11 columns as shown above


model2.add(Dense(units=8,activation='relu',kernel_initializer='he_normal'))
# hidden layer
model2.add(Dense(1,activation='sigmoid'))                        # binary classification for Churn or not



# Create optimizer with default learning rate
# Compile the model
model2.compile(Adam(lr=0.001),loss='binary_crossentropy',metrics=['accuracy'])

#create model summary 
model2.summary()

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_7 (Dense)              (None, 8)                 96        
_________________________________________________________________
dense_8 (Dense)              (None, 8)                 72        
_________________________________________________________________
dense_9 (Dense)              (None, 1)                 9         
=================================================================
Total params: 177
Trainable params: 177
Non-trainable params: 0
_________________________________________________________________


#fitting the model
history=model2.fit(X_train,y_train,batch_size=20,epochs=100,validation_split=0.2 ,class_weight=class_weights)

Epoch 1/100
320/320 [==============================] - 2s 3ms/step - loss: 0.8527 - accuracy: 0.6723 - val_loss: 0.6616 - val_accuracy: 0.6206
Epoch 2/100
320/320 [==============================] - 1s 2ms/step - loss: 0.6610 - accuracy: 0.6124 - val_loss: 0.6318 - val_accuracy: 0.6269
Epoch 3/100
320/320 [==============================] - 1s 2ms/step - loss: 0.6260 - accuracy: 0.6325 - val_loss: 0.6154 - val_accuracy: 0.6356
Epoch 4/100
320/320 [==============================] - 1s 2ms/step - loss: 0.6047 - accuracy: 0.6619 - val_loss: 0.6067 - val_accuracy: 0.6594
Epoch 5/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5957 - accuracy: 0.6685 - val_loss: 0.5756 - val_accuracy: 0.6931
Epoch 6/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5819 - accuracy: 0.6962 - val_loss: 0.5757 - val_accuracy: 0.6956
Epoch 7/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5600 - accuracy: 0.7013 - val_loss: 0.5769 - val_accuracy: 0.7044
Epoch 8/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5803 - accuracy: 0.6910 - val_loss: 0.5716 - val_accuracy: 0.7100
Epoch 9/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5667 - accuracy: 0.7028 - val_loss: 0.5665 - val_accuracy: 0.7169
Epoch 10/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5611 - accuracy: 0.7136 - val_loss: 0.5535 - val_accuracy: 0.7237
Epoch 11/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5592 - accuracy: 0.7163 - val_loss: 0.5453 - val_accuracy: 0.7275
Epoch 12/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5472 - accuracy: 0.7417 - val_loss: 0.5515 - val_accuracy: 0.7287
Epoch 13/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5519 - accuracy: 0.7288 - val_loss: 0.5324 - val_accuracy: 0.7356
Epoch 14/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5411 - accuracy: 0.7473 - val_loss: 0.5365 - val_accuracy: 0.7331
Epoch 15/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5396 - accuracy: 0.7291 - val_loss: 0.5395 - val_accuracy: 0.7337
Epoch 16/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5352 - accuracy: 0.7365 - val_loss: 0.5301 - val_accuracy: 0.7337
Epoch 17/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5302 - accuracy: 0.7495 - val_loss: 0.5266 - val_accuracy: 0.7356
Epoch 18/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5229 - accuracy: 0.7513 - val_loss: 0.5448 - val_accuracy: 0.7256
Epoch 19/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5187 - accuracy: 0.7455 - val_loss: 0.5323 - val_accuracy: 0.7375
Epoch 20/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5150 - accuracy: 0.7523 - val_loss: 0.5361 - val_accuracy: 0.7256
Epoch 21/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5231 - accuracy: 0.7479 - val_loss: 0.5072 - val_accuracy: 0.7500
Epoch 22/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5114 - accuracy: 0.7610 - val_loss: 0.5156 - val_accuracy: 0.7437
Epoch 23/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5131 - accuracy: 0.7537 - val_loss: 0.5016 - val_accuracy: 0.7569
Epoch 24/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5243 - accuracy: 0.7558 - val_loss: 0.4905 - val_accuracy: 0.7656
Epoch 25/100
320/320 [==============================] - 1s 2ms/step - loss: 0.5086 - accuracy: 0.7646 - val_loss: 0.5157 - val_accuracy: 0.7425
Epoch 26/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4863 - accuracy: 0.7695 - val_loss: 0.5124 - val_accuracy: 0.7462
Epoch 27/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4915 - accuracy: 0.7597 - val_loss: 0.5054 - val_accuracy: 0.7481
Epoch 28/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4939 - accuracy: 0.7648 - val_loss: 0.5068 - val_accuracy: 0.7513
Epoch 29/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4899 - accuracy: 0.7641 - val_loss: 0.4905 - val_accuracy: 0.7619
Epoch 30/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4861 - accuracy: 0.7738 - val_loss: 0.5001 - val_accuracy: 0.7588
Epoch 31/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4820 - accuracy: 0.7716 - val_loss: 0.4861 - val_accuracy: 0.7681
Epoch 32/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4673 - accuracy: 0.7854 - val_loss: 0.4889 - val_accuracy: 0.7675
Epoch 33/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4909 - accuracy: 0.7803 - val_loss: 0.4899 - val_accuracy: 0.7700
Epoch 34/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4655 - accuracy: 0.7798 - val_loss: 0.4951 - val_accuracy: 0.7631
Epoch 35/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4625 - accuracy: 0.7908 - val_loss: 0.4903 - val_accuracy: 0.7694
Epoch 36/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4646 - accuracy: 0.7836 - val_loss: 0.4693 - val_accuracy: 0.7812
Epoch 37/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4722 - accuracy: 0.7873 - val_loss: 0.4699 - val_accuracy: 0.7819
Epoch 38/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4735 - accuracy: 0.7979 - val_loss: 0.4769 - val_accuracy: 0.7775
Epoch 39/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4415 - accuracy: 0.8018 - val_loss: 0.4815 - val_accuracy: 0.7756
Epoch 40/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4710 - accuracy: 0.7851 - val_loss: 0.4873 - val_accuracy: 0.7688
Epoch 41/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4477 - accuracy: 0.7892 - val_loss: 0.4678 - val_accuracy: 0.7825
Epoch 42/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4611 - accuracy: 0.7858 - val_loss: 0.4599 - val_accuracy: 0.7900
Epoch 43/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4601 - accuracy: 0.7962 - val_loss: 0.4690 - val_accuracy: 0.7825
Epoch 44/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4688 - accuracy: 0.7843 - val_loss: 0.4621 - val_accuracy: 0.7831
Epoch 45/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4694 - accuracy: 0.7887 - val_loss: 0.4584 - val_accuracy: 0.7869
Epoch 46/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4656 - accuracy: 0.7872 - val_loss: 0.4942 - val_accuracy: 0.7631
Epoch 47/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4467 - accuracy: 0.7938 - val_loss: 0.4805 - val_accuracy: 0.7788
Epoch 48/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4631 - accuracy: 0.7933 - val_loss: 0.4695 - val_accuracy: 0.7856
Epoch 49/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4656 - accuracy: 0.7886 - val_loss: 0.4778 - val_accuracy: 0.7750
Epoch 50/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4581 - accuracy: 0.7911 - val_loss: 0.4779 - val_accuracy: 0.7738
Epoch 51/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4514 - accuracy: 0.7873 - val_loss: 0.4774 - val_accuracy: 0.7713
Epoch 52/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4641 - accuracy: 0.7819 - val_loss: 0.4667 - val_accuracy: 0.7825
Epoch 53/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4590 - accuracy: 0.7915 - val_loss: 0.4735 - val_accuracy: 0.7756
Epoch 54/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4521 - accuracy: 0.7848 - val_loss: 0.4453 - val_accuracy: 0.7981
Epoch 55/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4422 - accuracy: 0.8063 - val_loss: 0.4732 - val_accuracy: 0.7806
Epoch 56/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4522 - accuracy: 0.7977 - val_loss: 0.4710 - val_accuracy: 0.7788
Epoch 57/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4766 - accuracy: 0.7838 - val_loss: 0.4642 - val_accuracy: 0.7850
Epoch 58/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4457 - accuracy: 0.7964 - val_loss: 0.4929 - val_accuracy: 0.7644
Epoch 59/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4578 - accuracy: 0.7827 - val_loss: 0.4856 - val_accuracy: 0.7681
Epoch 60/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4535 - accuracy: 0.7938 - val_loss: 0.4525 - val_accuracy: 0.7937
Epoch 61/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4501 - accuracy: 0.8071 - val_loss: 0.4711 - val_accuracy: 0.7831
Epoch 62/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4552 - accuracy: 0.7923 - val_loss: 0.4704 - val_accuracy: 0.7788
Epoch 63/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4559 - accuracy: 0.7950 - val_loss: 0.4709 - val_accuracy: 0.7794
Epoch 64/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4530 - accuracy: 0.7904 - val_loss: 0.4712 - val_accuracy: 0.7769
Epoch 65/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4344 - accuracy: 0.8049 - val_loss: 0.4841 - val_accuracy: 0.7681
Epoch 66/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4398 - accuracy: 0.8016 - val_loss: 0.4663 - val_accuracy: 0.7812
Epoch 67/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4528 - accuracy: 0.7953 - val_loss: 0.4711 - val_accuracy: 0.7788
Epoch 68/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4443 - accuracy: 0.7993 - val_loss: 0.4721 - val_accuracy: 0.7763
Epoch 69/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4311 - accuracy: 0.8040 - val_loss: 0.4695 - val_accuracy: 0.7775
Epoch 70/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4494 - accuracy: 0.7966 - val_loss: 0.4496 - val_accuracy: 0.7906
Epoch 71/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4529 - accuracy: 0.7958 - val_loss: 0.4480 - val_accuracy: 0.7912
Epoch 72/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4519 - accuracy: 0.7993 - val_loss: 0.4351 - val_accuracy: 0.8025
Epoch 73/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4387 - accuracy: 0.8096 - val_loss: 0.4706 - val_accuracy: 0.7788
Epoch 74/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4422 - accuracy: 0.8010 - val_loss: 0.4572 - val_accuracy: 0.7837
Epoch 75/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4336 - accuracy: 0.8097 - val_loss: 0.5044 - val_accuracy: 0.7487
Epoch 76/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4406 - accuracy: 0.7860 - val_loss: 0.4667 - val_accuracy: 0.7756
Epoch 77/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4529 - accuracy: 0.7958 - val_loss: 0.4697 - val_accuracy: 0.7744
Epoch 78/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4350 - accuracy: 0.7985 - val_loss: 0.4524 - val_accuracy: 0.7862
Epoch 79/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4460 - accuracy: 0.8060 - val_loss: 0.4601 - val_accuracy: 0.7781
Epoch 80/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4427 - accuracy: 0.8014 - val_loss: 0.4653 - val_accuracy: 0.7800
Epoch 81/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4382 - accuracy: 0.8059 - val_loss: 0.4633 - val_accuracy: 0.7788
Epoch 82/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4277 - accuracy: 0.8089 - val_loss: 0.4672 - val_accuracy: 0.7788
Epoch 83/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4339 - accuracy: 0.8068 - val_loss: 0.4857 - val_accuracy: 0.7713
Epoch 84/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4465 - accuracy: 0.7967 - val_loss: 0.4712 - val_accuracy: 0.7725
Epoch 85/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4509 - accuracy: 0.7960 - val_loss: 0.4600 - val_accuracy: 0.7812
Epoch 86/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4459 - accuracy: 0.7989 - val_loss: 0.4548 - val_accuracy: 0.7912
Epoch 87/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4451 - accuracy: 0.8058 - val_loss: 0.4609 - val_accuracy: 0.7812
Epoch 88/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4487 - accuracy: 0.7940 - val_loss: 0.4740 - val_accuracy: 0.7706
Epoch 89/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4370 - accuracy: 0.8015 - val_loss: 0.4614 - val_accuracy: 0.7819
Epoch 90/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4548 - accuracy: 0.7969 - val_loss: 0.4794 - val_accuracy: 0.7713
Epoch 91/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4361 - accuracy: 0.8035 - val_loss: 0.4937 - val_accuracy: 0.7588
Epoch 92/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4389 - accuracy: 0.7959 - val_loss: 0.4675 - val_accuracy: 0.7781
Epoch 93/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4448 - accuracy: 0.7981 - val_loss: 0.4637 - val_accuracy: 0.7819
Epoch 94/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4394 - accuracy: 0.8061 - val_loss: 0.4652 - val_accuracy: 0.7788
Epoch 95/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4399 - accuracy: 0.7961 - val_loss: 0.4423 - val_accuracy: 0.7981
Epoch 96/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4470 - accuracy: 0.8029 - val_loss: 0.4813 - val_accuracy: 0.7681
Epoch 97/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4341 - accuracy: 0.7962 - val_loss: 0.4718 - val_accuracy: 0.7775
Epoch 98/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4639 - accuracy: 0.7906 - val_loss: 0.4529 - val_accuracy: 0.7881
Epoch 99/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4377 - accuracy: 0.8030 - val_loss: 0.4594 - val_accuracy: 0.7831
Epoch 100/100
320/320 [==============================] - 1s 2ms/step - loss: 0.4466 - accuracy: 0.7991 - val_loss: 0.4526 - val_accuracy: 0.7894


# Capturing learning history per epoch
hist  = pd.DataFrame(history.history)
hist['epoch'] = history.epoch

# Plotting accuracy at different epochs
plt.plot(hist['loss'])
plt.plot(hist['val_loss'])
plt.legend(("train" , "valid") , loc =0)

<matplotlib.legend.Legend at 0x7fe3cef7b210>


score = model2.evaluate(X_test, y_test)

63/63 [==============================] - 0s 2ms/step - loss: 0.4505 - accuracy: 0.7940


## Confusion Matrix 
import seaborn as sn
y_pred1 = model2.predict(X_test)
for i in range(len(y_test)):
    if y_pred1[i]>0.5:
        y_pred1[i]=1 
    else:
        y_pred1[i]=0



cm2=confusion_matrix(y_test, y_pred1)
labels = ['True Negative','False Positive','False Negative','True Positive']
categories = [ 'Retained','Exited']
make_confusion_matrix(cm2, 
                      group_names=labels,
                      categories=categories, 
                      cmap='Blues')


#AUC ROC curve
from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve

DNN_roc_auc = roc_auc_score(y_test, model2.predict(X_test))
fpr, tpr, thresholds = roc_curve(y_test, model2.predict(X_test))

# calculate the g-mean for each threshold
gmeans = np.sqrt(tpr * (1-fpr))


# locate the index of the largest g-mean
ix = np.argmax(gmeans)
print('Best Threshold=%f, G-Mean=%.3f' % (thresholds[ix], gmeans[ix]))


plt.figure()

plt.scatter(fpr[ix], tpr[ix], marker='o', color='black', label='Best')
plt.plot(fpr, tpr, label='Model 1 (area = %0.2f)' % DNN_roc_auc)
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
plt.savefig('ROC')
plt.show()

Best Threshold=0.514440, G-Mean=0.778


y_pred1 = model2.predict(X_test)
for i in range(len(y_test)):
    if y_pred1[i]>0.514440:
        y_pred1[i]=1 
    else:
        y_pred1[i]=0



cm2=confusion_matrix(y_test, y_pred1)
labels = ['True Negative','False Positive','False Negative','True Positive']
categories = [ 'Retained','Exited']
make_confusion_matrix(cm2, 
                      group_names=labels,
                      categories=categories, 
                      cmap='Blues')

	RowNumber	CustomerId	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
count	10000.00000	1.000000e+04	10000.000000	10000.000000	10000.000000	10000.000000	10000.000000	10000.00000	10000.000000	10000.000000	10000.000000
mean	5000.50000	1.569094e+07	650.528800	38.921800	5.012800	76485.889288	1.530200	0.70550	0.515100	100090.239881	0.203700
std	2886.89568	7.193619e+04	96.653299	10.487806	2.892174	62397.405202	0.581654	0.45584	0.499797	57510.492818	0.402769
min	1.00000	1.556570e+07	350.000000	18.000000	0.000000	0.000000	1.000000	0.00000	0.000000	11.580000	0.000000
25%	2500.75000	1.562853e+07	584.000000	32.000000	3.000000	0.000000	1.000000	0.00000	0.000000	51002.110000	0.000000
50%	5000.50000	1.569074e+07	652.000000	37.000000	5.000000	97198.540000	1.000000	1.00000	1.000000	100193.915000	0.000000
75%	7500.25000	1.575323e+07	718.000000	44.000000	7.000000	127644.240000	2.000000	1.00000	1.000000	149388.247500	0.000000
max	10000.00000	1.581569e+07	850.000000	92.000000	10.000000	250898.090000	4.000000	1.00000	1.000000	199992.480000	1.000000

Exited	0	1
Geography
France	0.838452	0.161548
Germany	0.675568	0.324432
Spain	0.833266	0.166734

Exited	0	1
Tenure
0	0.769976	0.230024
1	0.775845	0.224155
2	0.808206	0.191794
3	0.788900	0.211100
4	0.794742	0.205258
5	0.793478	0.206522
6	0.797311	0.202689
7	0.827821	0.172179
8	0.807805	0.192195
9	0.783537	0.216463
10	0.793878	0.206122

Exited	0	1
NumOfProducts
1	0.722856	0.277144
2	0.924183	0.075817
3	0.172932	0.827068
4	0.000000	1.000000

Exited	0	1
HasCrCard
0	0.791851	0.208149
1	0.798157	0.201843

Background and Context¶

Objective¶

Data Description¶

Data Dictionary:¶

Import Libraries¶

Import data¶

Read in data and review samples¶

Read in data¶

Review Sample data¶

Change the object type variables to Categorical variables for space¶

Review counts of the category variables¶

Check unique values¶

Summary of Data¶

Univariate analysis¶

Create Histograms and Boxplots¶

CDF plot of numerical variables¶

Review Categorical Variables¶

Bivariate analysis¶

Review Correlation Heat Map¶

Reviews crosstab of categorical varibles with proportion of Exited¶

Review the continous variables using distribrution plots¶

Create customer profile by Exited status¶

Additional Deep Dives¶

Since Age, Balance and Geography appear to be predictive variables. Deeper dive into understanding them is required¶

Data Pre-processing¶

Split the target variable and predictors - Split the data into train and test - Rescale the data¶

Splitting the Data into train and test set¶

Create Model¶

Evaluation¶

Functions to create Confusion Matrix and Scoring Metrics¶

Review ROC Curve to see the optimal threshold¶

A mixture of recall and precision is the goal. The reason is that we don't want to spend too much money on marketing for retention by targeting everyone, but we also don't want to miss the customers who are high risk of exiting.¶

Evaluation¶

Review ROC Curve to see the optimal threshold¶

Conclusion¶

Confusion Matrix¶

`Important Metric`¶

Important Features¶

Final Summary¶

Business Recommendations¶

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary
5987	5988	15636634	Lindon	630	Germany	Female	25	7	79656.81	1	1	0	93524.22
3169	3170	15688172	Tai	677	Spain	Male	40	5	0.00	2	1	0	88947.56
5562	5563	15614361	Liao	620	Spain	Male	42	9	121490.05	1	1	1	29296.74
6554	6555	15632576	Yashina	520	France	Male	31	4	93249.40	1	1	0	77335.75
1859	1860	15681956	Bailey	684	France	Male	34	9	0.00	2	1	1	65257.57

	count	unique	top	freq
Surname	10000	2932	Smith	32
Geography	10000	3	France	5014
Gender	10000	2	Male	5457

	RowNumber	CustomerId	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary
Exited
0	5024.694964	1.569117e+07	651.853196	37.408389	5.033279	72745.296779	1.544267	0.707146	0.554565	99738.391772
1	4905.917526	1.569005e+07	645.351497	44.837997	4.932744	91108.539337	1.475209	0.699067	0.360825	101465.677531

	RowNumber	CustomerId	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
Geography
France	5025.228560	1.569065e+07	649.668329	38.511767	5.004587	62092.636516	1.530913	0.706621	0.516753	99899.180814	0.161548
Germany	5000.278996	1.569056e+07	651.453567	39.771622	5.009964	119730.116134	1.519729	0.713830	0.497409	101113.435102	0.324432
Spain	4950.667743	1.569192e+07	651.333872	38.890997	5.032297	61818.147763	1.539362	0.694792	0.529673	99440.572281	0.166734

	CreditScore	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Geography_Germany	Geography_Spain
0	-0.326221	-1.095988	0.293517	-1.041760	-1.225848	-0.911583	0.646092	0.970243	0.021886	-0.578736	-0.573809
1	-0.440036	-1.095988	0.198164	-1.387538	0.117350	-0.911583	-1.547768	0.970243	0.216534	-0.578736	1.742740
2	-1.536794	-1.095988	0.293517	1.032908	1.333053	2.527057	0.646092	-1.030670	0.240687	-0.578736	-0.573809
3	0.501521	-1.095988	0.007457	-1.387538	-1.225848	0.807737	-1.547768	-1.030670	-0.108918	-0.578736	-0.573809
4	2.063884	-1.095988	0.388871	-1.041760	0.785728	-0.911583	0.646092	0.970243	-0.365276	-0.578736	1.742740
...	...	...	...	...	...	...	...	...	...	...	...
9995	1.246488	0.912419	0.007457	-0.004426	-1.225848	0.807737	0.646092	-1.030670	-0.066419	-0.578736	-0.573809
9996	-1.391939	0.912419	-0.373958	1.724464	-0.306379	-0.911583	0.646092	0.970243	0.027988	-0.578736	-0.573809
9997	0.604988	-1.095988	-0.278604	0.687130	-1.225848	-0.911583	-1.547768	0.970243	-1.008643	-0.578736	-0.573809
9998	1.256835	0.912419	0.293517	-0.695982	-0.022608	0.807737	0.646092	-1.030670	-0.125231	1.727904	-0.573809
9999	1.463771	-1.095988	-1.041433	-0.350204	0.859965	-0.911583	0.646092	-1.030670	-1.076370	-0.578736	-0.573809

Exited	0	1
Gender
Female	0.749285	0.250715
Male	0.835441	0.164559

Exited	0	1
IsActiveMember
0	0.731491	0.268509
1	0.857309	0.142691

		mean	count
		Age	Age
Geography	Exited
France	0	37.235966	4204
France	1	45.133333	810
Germany	0	37.311504	1695
Germany	1	44.894349	814
Spain	0	37.839147	2064
Spain	1	44.147700	413

Background and Context¶

Objective¶

Data Description¶

Data Dictionary:¶

Import Libraries¶

Import data¶

Read in data and review samples¶

Read in data¶

Review Sample data¶

Change the object type variables to Categorical variables for space¶

Review counts of the category variables¶

Check unique values¶

Summary of Data¶

Univariate analysis¶

Create Histograms and Boxplots¶

CDF plot of numerical variables¶

Review Categorical Variables¶

Bivariate analysis¶

Review Correlation Heat Map¶

Reviews crosstab of categorical varibles with proportion of Exited¶

Review the continous variables using distribrution plots¶

Create customer profile by Exited status¶

Additional Deep Dives¶

Since Age, Balance and Geography appear to be predictive variables. Deeper dive into understanding them is required¶

Data Pre-processing¶

Split the target variable and predictors - Split the data into train and test - Rescale the data¶

Splitting the Data into train and test set¶

Create Model¶

Evaluation¶

Functions to create Confusion Matrix and Scoring Metrics¶

Review ROC Curve to see the optimal threshold¶

A mixture of recall and precision is the goal. The reason is that we don't want to spend too much money on marketing for retention by targeting everyone, but we also don't want to miss the customers who are high risk of exiting.¶

Evaluation¶

Review ROC Curve to see the optimal threshold¶

Conclusion¶

Confusion Matrix¶

Important Metric¶

Important Features¶

Final Summary¶

Business Recommendations¶

`Important Metric`¶